Repo đang lênCập nhật hằng ngày từ GitHub

Blazing fast framework for fine-tuning similarity learning models

Một cuốn sách về Học Sâu đề cập đến nhiều framework phổ biến, được sử dụng trên 300 trường Đại học từ 55 đất nước bao gồm MIT, Stanford, Harvard, và Cambridge.

A personal wearable AI that runs locally

Is ChatGPT Good at Search? LLMs as Re-Ranking Agent [EMNLP 2023 Outstanding Paper Award]

A.S.E (AICGSecEval) is a repository-level AI-generated code security evaluation benchmark developed by Tencent Wukong Code Security Team.

AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.

Towards deepfake detection that actually works

MICA - Towards Metrical Reconstruction of Human Faces [ECCV2022]

The most complete open-source Swift package for interacting with OpenAI's public API.

Recap AI for YouTube summaries, a searchable transcript and chat about the video

eBPF (extended Berkeley Packet Filter) Guide. Learn all about the eBPF Tools and Libraries for Security, Monitoring , and Networking.

[CVPR 2021] Self-supervised depth estimation from short sequences

Dress Code: High-Resolution Multi-Category Virtual Try-On. ECCV 2022

PyTorch Code for Energy-Based Transformers paper -- generalizable reasoning and scalable learning

End-to-end Lane Detection for Self-Driving Cars (ICCV 2019 Workshop)

Open diffusion language model for code generation — releasing pretraining, evaluation, inference, and checkpoints.

DFloat11 [NeurIPS '25]: Lossless Compression of LLMs and DiTs for Efficient GPU Inference

Memento is a Python app that records everything you do on your computer and lets you go back in time, search, and chat with a LLM (Large Language Model) to find back information about what you did.

Ego4d dataset repository. Download the dataset, visualize, extract features & example usage of the dataset

Variational Autoencoder and Conditional Variational Autoencoder on MNIST in PyTorch

The most comprehensive DeepSeek Harness plugin market — refreshed daily, sourced across the Internet, reviewed before publishing.

The llama-cpp-agent framework is a tool designed for easy interaction with Large Language Models (LLMs). Allowing users to chat with LLM models, execute structured function calls and get structured output. Works also with models not fine-tuned to JSON output and function calls.

The unofficial OpenAI SDK for Dart & Flutter. Full API coverage + OpenAI-compatible providers (Azure, DeepSeek, LM Studio, Ollama): Responses, Chat, Realtime, Videos, Batch, Fine-tuning.

All-in-one Toolbox for Computer Vision Research.

An implementation of Grad-CAM with keras

ANOLISA (Agentic Nexus Operating Layer & Interface System Architecture) | Agentic OS with runtime, security, observability, and Tokenless response compression for lower token usage and cost.

✨✨Latest Papers and Benchmarks in Reasoning with Foundation Models

The main component of AI DIAL, which provides unified API to different chat completion and embedding models, assistants, and applications

Querying local documents, powered by LLM

Fast, accurate and easy to run dense optical flow with python wrapper

Official implementation of OneDiffusion paper (CVPR 2025)

a reimplementation of PWC-Net in PyTorch that matches the official Caffe version

Cell type annotation for single-cell RNA-seq using multi-LLM consensus

RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios

Code and data for "AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks" [TMLR 2024]

Fast, offline OCR for Node.js & C++. PP-OCRv6 with Core ML / WebGPU hardware acceleration — recognize text in images with confidence scores & coordinates. npm: @arcships/light-ocr

A collection of ComfyUI custom nodes. ⚠️ WARNING: This repo is no longer maintained.

使用 OpenAI API 给文本进行润色和语法纠错的 Bob 插件！完美代替 Grammarly！Licensed under CC BY-NC-SA 4.0

☝🏻 一个好玩的个人微信机器人程序(DaenDLL、VLW)，插件开发，查天气，ChatGPT聊天，设置定时任务，公众号监控转发...

Extract video features from raw videos using multiple GPUs. We support RAFT flow frames as well as S3D, I3D, R(2+1)D, VGGish, CLIP, and TIMM models.

A pytorch reimplementation of CheXNet

数学建模和机器学习/深度学习/大模型的笔记和资料（持续更新中......）。

An open harness to simulate and deploy PX4/ArduPilot/Betaflight perception-based drone swarms with ROS2, YOLO, NVIDIA Jetson

Aora Bot：代码绘制的网页角色引擎。71 个角色、16 种脸、44 种动画状态、三种画风，另有 7 个节日主题共 122 个角色。支持 React、Web Component 与头像接口。（原 Emotion Ball 表情馆）

On-device AI for Flutter — Gemma and other LLMs, multimodal, function calling, embeddings, RAG and speech on Android, iOS, Web, macOS, Windows and Linux.

Agent harness and tookit for building AI agents and agentic applications. CLI and SDKs included

AigoTools can help users quickly create and manage website directory, with built-in site auto-crawling features, and also provides internationalization, SEO, image storage, and other functions. It allows users to quickly deploy their own directory site online.

"ChatBot" AI application, supporting GPT, Gemini Pro, Cohere & Ollama models

Simple A3C implementation with pytorch + multiprocessing

[IEEE TGRS 2024] ChangeMamba: Remote Sensing Change Detection Based on Spatio-Temporal State Space Model